Trust Assessment
postiz-clawed received a trust score of 84/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Authentication Cookie Stored in Insecure /tmp Directory, Potential Arbitrary File Upload and Data Exfiltration via Unsanitized Paths.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 12, 2026 (commit 5acc5677). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Arbitrary File Upload and Data Exfiltration via Unsanitized Paths The documentation provides an example for uploading an image using `curl -F 'file=@/path/to/image.png'`. If the skill's implementation allows users to specify arbitrary file paths for upload without proper validation and sanitization, it could lead to several vulnerabilities. A malicious actor could upload sensitive files from the agent's filesystem (data exfiltration) or potentially exploit path traversal to overwrite critical system files, depending on the server-side handling. This also implies the skill might request broad filesystem read permissions. When implementing file upload functionality, strictly validate and sanitize all user-provided file paths. Restrict file access to only necessary directories and file types. Ensure the LLM's execution environment has minimal necessary filesystem permissions. If the skill is intended to upload user-provided files, ensure they are uploaded from a secure, isolated user-specific directory, not arbitrary system paths. | LLM | SKILL.md:139 | |
| MEDIUM | Authentication Cookie Stored in Insecure /tmp Directory The skill's authentication mechanism, as described in the documentation, saves session cookies to `/tmp/postiz-cookies.txt`. The `/tmp` directory is typically world-writable and not designed for secure storage of sensitive data. In a shared or compromised environment, these cookies could be accessed by other processes or users, leading to unauthorized access to the Postiz API. Store authentication tokens or cookies in a more secure, isolated, and permission-restricted location. Consider using environment variables, a secure credential store, or a dedicated, permission-controlled directory for sensitive data. Avoid using `/tmp` for persistent or sensitive information. | LLM | SKILL.md:34 |
Scan History
Embed Code
[](https://skillshield.io/report/02a06d935dd4af9d)
Powered by SkillShield